Unlocking Guidance for Discrete State-Space Diffusion and Flow Models

2024/06/03 by Hunter Nisonoff, Nisonoff, Hunter, Junhao Xiong +5 · 25 citations
Decision Sciences · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Simulation Techniques and Applications

paper · pdf · doi:10.48550/arxiv.2406.01572

openalex publication_date 2024/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has been realized using guidance on diffusion and flow models. However, these guidance approaches are not readily amenable to discrete state-space models. Consequently, we introduce a general and principled method for applying guidance on such models. Our method depends on leveraging continuous-time Markov processes on discrete state-spaces, which unlocks computational tractability for sampling from a desired guided distribution. We demonstrate the utility of our approach, Discrete Guidance, on a range of applications including guided generation of small-molecules, DNA sequences and protein sequences.

Cited by

• CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology
• Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
• MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching
• Guided Transfer Learning for Discrete Diffusion Models
• ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
• A Diffusion Model to Shrink Proteins While Maintaining Their Function
• How to make the most of your masked language model for protein engineering
• g-DPO: Scalable Preference Optimization for Protein Language Models
• Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
• Guided Star-Shaped Masked Diffusion
• Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
• Diffusion Alignment as Variational Expectation-Maximization
• Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
• AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance
• Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery
• RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance
• Guided Diffusion for the Discovery of New Superconductors
• TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
• Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
• Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
• d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation
• Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
• Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimization
• Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling
• MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Related

• Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
• Simple Guidance Mechanisms for Discrete Diffusion Models
• Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
• α-Flow: A Unified Framework for Continuous-State Discrete Flow Matching Models